Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    )

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Sơn
    -0.08
    baugh
    -0.07
    ">',↵
    -0.07
    .servers
    -0.06
    :';↵
    -0.06
    [z
    -0.06
     isa
    -0.06
    .describe
    -0.06
    FIELD
    -0.06
     Activity
    -0.06
    POSITIVE LOGITS
    UTURE
    0.07
    人
    0.07
     capital
    0.06
    SI
    0.06
     حقوق
    0.06
     счит
    0.06
    اپ
    0.06
     uncomp
    0.06
     Pl
    0.06
    pokemon
    0.06
    Act Density 0.006%

    No Known Activations